{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:47:05Z","timestamp":1765309625171,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":58,"publisher":"ACM","funder":[{"name":"National Nature Science Foundation of China","award":["62406073"],"award-info":[{"award-number":["62406073"]}]},{"name":"Shanghai Municipal Science and Technology Commission","award":["24511104000"],"award-info":[{"award-number":["24511104000"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3754812","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T06:56:44Z","timestamp":1761375404000},"page":"10728-10737","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Temporal-Conditioned Symbolic Alignment for Controllable Text-to-Music Generation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-0668-4462","authenticated-orcid":false,"given":"Zihao","family":"Zhang","sequence":"first","affiliation":[{"name":"East China Normal University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9146-051X","authenticated-orcid":false,"given":"Xingjiao","family":"Wu","sequence":"additional","affiliation":[{"name":"East China Normal University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-1965-867X","authenticated-orcid":false,"given":"Junjie","family":"Xu","sequence":"additional","affiliation":[{"name":"East China Normal University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4079-7897","authenticated-orcid":false,"given":"Tianlong","family":"Ma","sequence":"additional","affiliation":[{"name":"East China Normal University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-5039-8189","authenticated-orcid":false,"given":"Tangren","family":"Yao","sequence":"additional","affiliation":[{"name":"East China Normal University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2132-5993","authenticated-orcid":false,"given":"Wen","family":"Wu","sequence":"additional","affiliation":[{"name":"East China Normal University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4723-5486","authenticated-orcid":false,"given":"Liang","family":"He","sequence":"additional","affiliation":[{"name":"East China Normal University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"Musiclm: Generating music from text. arXiv preprint arXiv:2301.11325 .","author":"Agostinelli A.","year":"2023","unstructured":"Agostinelli, A., Denk, T.I., Borsos, Z., Engel, J., Verzetti, M., Caillon, A., Huang, Q., Jansen, A., Roberts, A., Tagliasacchi, M., et al., 2023. Musiclm: Generating music from text. arXiv preprint arXiv:2301.11325 ."},{"volume-title":"Audiolm: a language modeling approach to audio generation","author":"Borsos Z.","key":"e_1_3_2_2_2_1","unstructured":"Borsos, Z., Marinier, R., Vincent, D., Kharitonov, E., Pietquin, O., Sharifi, M., Roblek, D., Teboul, O., Grangier, D., Tagliasacchi, M., et al., 2023. Audiolm: a language modeling approach to audio generation. IEEE\/ACM transactions on audio, speech, and language processing 31, 2523-2533."},{"key":"e_1_3_2_2_3_1","first-page":"1206","volume-title":"Musicldm: Enhancing novelty in text-to-music generation using beatsynchronous mixup strategies, in: ICASSP","author":"Chen K.","year":"2024","unstructured":"Chen, K., Wu, Y., Liu, H., Nezhurina, M., Berg-Kirkpatrick, T., Dubnov, S., 2024. Musicldm: Enhancing novelty in text-to-music generation using beatsynchronous mixup strategies, in: ICASSP, IEEE. pp. 1206-1210."},{"key":"e_1_3_2_2_4_1","unstructured":"Chen R.T. Rubanova Y. Bettencourt J. Duvenaud D.K. 2018. Neural ordinary differential equations. Advances in neural information processing systems ."},{"key":"e_1_3_2_2_5_1","first-page":"47704","article-title":"Simple and controllable music generation","volume":"36","author":"Copet J.","year":"2023","unstructured":"Copet, J., Kreuk, F., Gat, I., Remez, T., Kant, D., Synnaeve, G., Adi, Y., D\u00e9fossez, A., 2023. Simple and controllable music generation. Advances in Neural Information Processing Systems 36, 47704-47720.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_6_1","volume-title":"Fma: A dataset for music analysis. arXiv preprint arXiv:1612.01840 .","author":"Defferrard M.","year":"2016","unstructured":"Defferrard, M., Benzi, K., Vandergheynst, P., Bresson, X., 2016. Fma: A dataset for music analysis. arXiv preprint arXiv:1612.01840 ."},{"key":"e_1_3_2_2_7_1","volume-title":"Jukebox: A generative model for music. arXiv preprint arXiv:2005.00341 .","author":"Dhariwal P.","year":"2020","unstructured":"Dhariwal, P., Jun, H., Payne, C., Kim, J.W., Radford, A., Sutskever, I., 2020. Jukebox: A generative model for music. arXiv preprint arXiv:2005.00341 ."},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446380"},{"key":"e_1_3_2_2_9_1","volume-title":"Singsong: Generating musical accompaniments from singing. arXiv preprint arXiv:2301.12662 .","author":"Donahue C.","year":"2023","unstructured":"Donahue, C., Caillon, A., Roberts, A., Manilow, E., Esling, P., Agostinelli, A., Verzetti, M., Simon, I., Pietquin, O., Zeghidour, N., et al., 2023. Singsong: Generating musical accompaniments from singing. arXiv preprint arXiv:2301.12662 ."},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095889"},{"key":"e_1_3_2_2_11_1","volume-title":"Forty-first international conference on machine learning.","author":"Esser P.","year":"2024","unstructured":"Esser, P., Kulal, S., Blattmann, A., Entezari, R., M\u00fcller, J., Saini, H., Levi, Y., Lorenz, D., Sauer, A., Boesel, F., et al., 2024. Scaling rectified flow transformers for highresolution image synthesis, in: Forty-first international conference on machine learning."},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1152\/jn.00209.2012"},{"key":"e_1_3_2_2_13_1","unstructured":"Fei Z. Fan M. Yu C. Huang J. 2024. Flux that plays music. arXiv preprint arXiv:2409.00587 ."},{"key":"e_1_3_2_2_14_1","unstructured":"Forsgren S. Martiros H. 2022a. Riffusion - Stable diffusion for real-time music generation. https:\/\/riffusion.com\/about ."},{"key":"e_1_3_2_2_15_1","unstructured":"Forsgren S. Martiros H. 2022b. Riffusion-stable diffusion for real-time music generation. URL https:\/\/riffusion. com ."},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"e_1_3_2_2_17_1","first-page":"5835","volume-title":"Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence","author":"Han B.","year":"2024","unstructured":"Han, B., Dai, J., Hao,W., He, X., Guo, D., Chen, J.,Wang, Y., Qian, Y., Song, X., 2024. Instructme: an instruction guided music edit framework with latent diffusion models, in: Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence, pp. 5835-5843."},{"key":"e_1_3_2_2_18_1","volume-title":"Beatnet: A real-time music integrated beat and downbeat tracker","author":"Heydari M.","year":"2021","unstructured":"Heydari, M., Cwitkowitz, F., Duan, Z., 2021. Beatnet: A real-time music integrated beat and downbeat tracker. International Society for Music Information Retrieval ."},{"key":"e_1_3_2_2_19_1","unstructured":"Ho J. Jain A. Abbeel P. 2020. Denoising diffusion probabilistic models. Advances in neural information processing systems 33 6840-6851."},{"key":"e_1_3_2_2_20_1","first-page":"28708","article-title":"Masked autoencoders that listen","volume":"35","author":"Huang P.Y.","year":"2022","unstructured":"Huang, P.Y., Xu, H., Li, J., Baevski, A., Auli, M., Galuba,W., Metze, F., Feichtenhofer, C., 2022a. Masked autoencoders that listen. Advances in Neural Information Processing Systems 35, 28708-28720.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_21_1","volume-title":"Ismir 2022 Hybrid Conference.","author":"Huang Q.","year":"2022","unstructured":"Huang, Q., Jansen, A., Lee, J., Ganti, R., Li, J.Y., Ellis, D.P., 2022b. Mulan: A joint embedding of music audio and natural language, in: Ismir 2022 Hybrid Conference."},{"key":"e_1_3_2_2_22_1","unstructured":"Huang Q. Park D.S. Wang T. Denk T.I. Ly A. Chen N. Zhang Z. Zhang Z. Yu J. Frank C. et al. 2023a. Noise2music: Text-conditioned music generation with diffusion models. arXiv preprint arXiv:2302.03917 ."},{"key":"e_1_3_2_2_23_1","first-page":"13916","volume-title":"International Conference on Machine Learning, PMLR.","author":"Huang R.","year":"2023","unstructured":"Huang, R., Huang, J., Yang, D., Ren, Y., Liu, L., Li, M., Ye, Z., Liu, J., Yin, X., Zhao, Z., 2023b. Make-an-audio: Text-to-audio generation with prompt-enhanced diffusion models, in: International Conference on Machine Learning, PMLR. pp. 13916-13932."},{"key":"e_1_3_2_2_24_1","volume-title":"20th International Society for Music Information Retrieval Conference (ISMIR)","author":"Jonggwon P.","year":"2019","unstructured":"Jonggwon, P., Kyoyun, C., Sungwook, J., Dokyun, K., Jonghun, P., 2019. A bidirectional transformer for musical chord recognition, in: 20th International Society for Music Information Retrieval Conference (ISMIR), Delft, The Netherlands."},{"key":"e_1_3_2_2_25_1","first-page":"2350","article-title":"Fr\u00e9chet audio distance: A reference-free metric for evaluating music enhancement algorithms","volume":"2019","author":"Kilgour K.","year":"2019","unstructured":"Kilgour, K., Zuluaga, M., Roblek, D., Sharifi, M., 2019. Fr\u00e9chet audio distance: A reference-free metric for evaluating music enhancement algorithms, in: Proc. Interspeech 2019, pp. 2350-2354.","journal-title":"Proc. Interspeech"},{"key":"e_1_3_2_2_26_1","volume-title":"Diffwave: A versatile diffusion model for audio synthesis. arXiv preprint arXiv:2009.09761 .","author":"Kong Z.","year":"2020","unstructured":"Kong, Z., Ping, W., Huang, J., Zhao, K., Catanzaro, B., 2020. Diffwave: A versatile diffusion model for audio synthesis. arXiv preprint arXiv:2009.09761 ."},{"key":"e_1_3_2_2_27_1","first-page":"2753","article-title":"Efficient training of audio transformers with patchout","volume":"2022","author":"Koutini K.","year":"2022","unstructured":"Koutini, K., Schl\u00fcter, J., Eghbal-zadeh, H., Widmer, G., 2022. Efficient training of audio transformers with patchout, in: Proc. Interspeech 2022, pp. 2753-2757.","journal-title":"Proc. Interspeech"},{"key":"e_1_3_2_2_28_1","volume-title":"The Eleventh International Conference on Learning Representations.","author":"Kreuk F.","year":"2023","unstructured":"Kreuk, F., Synnaeve, G., Polyak, A., Singer, U., D\u00e9fossez, A., Copet, J., Parikh, D., Taigman, Y., Adi, Y., 2023. Audiogen: Textually guided audio generation, in: The Eleventh International Conference on Learning Representations."},{"key":"e_1_3_2_2_29_1","first-page":"17450","article-title":"Efficient neural music generation","volume":"36","author":"Lam M.W.","year":"2023","unstructured":"Lam, M.W., Tian, Q., Li, T., Yin, Z., Feng, S., Tu, M., Ji, Y., Xia, R., Ma, M., Song, X., et al., 2023. Efficient neural music generation. Advances in Neural Information Processing Systems 36, 17450-17463.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_30_1","volume-title":"Musicongen: Rhythm and chord control for transformer-based text-to-music generation. arXiv preprint arXiv:2407.15060 .","author":"Lan Y.H.","year":"2024","unstructured":"Lan, Y.H., Hsiao, W.Y., Cheng, H.C., Yang, Y.H., 2024. Musicongen: Rhythm and chord control for transformer-based text-to-music generation. arXiv preprint arXiv:2407.15060 ."},{"key":"e_1_3_2_2_31_1","volume-title":"Voicebox: Text-guided multilingual universal speech generation at scale. Advances in neural information processing systems 36, 14005-14034.","author":"Le M.","year":"2023","unstructured":"Le, M., Vyas, A., Shi, B., Karrer, B., Sari, L., Moritz, R., Williamson, M., Manohar, V., Adi, Y., Mahadeokar, J., et al., 2023. Voicebox: Text-guided multilingual universal speech generation at scale. Advances in neural information processing systems 36, 14005-14034."},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CAI59869.2024.00146"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123399"},{"key":"e_1_3_2_2_34_1","unstructured":"Lin L. Xia G. Jiang J. Zhang Y. 2023. Content-based controls for music large language modeling. arXiv preprint arXiv:2310.17162 ."},{"key":"e_1_3_2_2_35_1","unstructured":"Lipman Y. Chen R.T. Ben-Hamu H. Nickel M. Le M. 2022. Flow matching for generative modeling. arXiv preprint arXiv:2210.02747 ."},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680594"},{"key":"e_1_3_2_2_37_1","volume-title":"Audioldm: Text-to-audio generation with latent diffusion models. arXiv preprint arXiv:2301.12503 .","author":"Liu H.","year":"2023","unstructured":"Liu, H., Chen, Z., Yuan, Y., Mei, X., Liu, X., Mandic, D., Wang, W., Plumbley, M.D., 2023a. Audioldm: Text-to-audio generation with latent diffusion models. arXiv preprint arXiv:2301.12503 ."},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"crossref","unstructured":"Liu H. Huang R. Lin X. Xu W. Zheng M. Chen H. He J. Zhao Z. 2023b. Vit-tts: visual text-to-speech with scalable diffusion transformer. arXiv preprint arXiv:2305.12708 .","DOI":"10.18653\/v1\/2023.emnlp-main.990"},{"key":"e_1_3_2_2_39_1","author":"Liu H.","year":"2024","unstructured":"Liu, H., Yuan, Y., Liu, X., Mei, X., Kong, Q., Tian, Q., Wang, Y., Wang, W., Wang, Y., Plumbley, M.D., 2024b. Audioldm 2: Learning holistic audio generation with self-supervised pretraining. IEEE\/ACM Transactions on Audio, Speech, and Language Processing .","journal-title":"IEEE\/ACM Transactions on Audio, Speech, and Language Processing ."},{"key":"e_1_3_2_2_40_1","volume-title":"NeurIPS Machine Learning for Audio Workshop.","author":"Manco I.","year":"2023","unstructured":"Manco, I., Weck, B., Doh, S., Won, M., Zhang, Y., Bodganov, D., Wu, Y., Chen, K., Tovstogan, P., Benetos, E., et al., 2023. The song describer dataset: a corpus of audio captions for music-and-language evaluation, in: NeurIPS Machine Learning for Audio Workshop."},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937170"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"crossref","unstructured":"Norman-Haignere S.V. Kanwisher N. McDermott J.H. Conway B.R. 2019. Divergence in the functional organization of human and macaque auditory cortex revealed by fmri responses to harmonic tones. Nature neuroscience 22 1057-1060.","DOI":"10.1038\/s41593-019-0410-7"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"crossref","unstructured":"Papadimitriou I. Jurafsky D. 2020. Learning music helps you read: Using transfer to study linguistic structure in language models. arXiv preprint arXiv:2004.14601 .","DOI":"10.18653\/v1\/2020.emnlp-main.554"},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446869"},{"key":"e_1_3_2_2_46_1","unstructured":"Ramesh A. Dhariwal P. Nichol A. Chu C. Chen M. 2022. Hierarchical textconditional image generation with clip latents. arXiv preprint arXiv:2204.06125 1 3."},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5946971"},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_2_49_1","first-page":"399","volume-title":"2020 International Conference on Systems, Signals and Image Processing (IWSSIP), IEEE.","author":"Santana I.A.P.","year":"2020","unstructured":"Santana, I.A.P., Pinhelli, F., Donini, J., Catharin, L., Mangolin, R.B., Feltrim, V.D., Domingues, M.A., et al., 2020. Music4all: A new music database and its applications, in: 2020 International Conference on Systems, Signals and Image Processing (IWSSIP), IEEE. pp. 399-404."},{"key":"e_1_3_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.437"},{"key":"e_1_3_2_2_51_1","unstructured":"Tal O. Ziv A. Gat I. Kreuk F. Adi Y. 2024. Joint audio and symbolic conditioning for temporally controlled text-to-music generation. arXiv preprint arXiv:2406.10970 ."},{"key":"e_1_3_2_2_52_1","unstructured":"Tsai F.D. Wu S.L. Kim H. Chen B.Y. Cheng H.C. Yang Y.H. 2024. Audio prompt adapter: Unleashing music editing abilities for text-to-music with lightweight finetuning ."},{"key":"e_1_3_2_2_53_1","volume-title":"Audiobox: Unified audio generation with natural language prompts. arXiv preprint arXiv:2312.15821 .","author":"Vyas A.","year":"2023","unstructured":"Vyas, A., Shi, B., Le, M., Tjandra, A., Wu, Y.C., Guo, B., Zhang, J., Zhang, X., Adkins, R., Ngan, W., et al., 2023. Audiobox: Unified audio generation with natural language prompts. arXiv preprint arXiv:2312.15821 ."},{"key":"e_1_3_2_2_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3399026"},{"key":"e_1_3_2_2_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3270726"},{"key":"e_1_3_2_2_56_1","first-page":"1","volume-title":"ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE.","author":"Wu Y.","year":"2023","unstructured":"Wu, Y., Chen, K., Zhang, T., Hui, Y., Berg-Kirkpatrick, T., Dubnov, S., 2023. Largescale contrastive language-audio pretraining with feature fusion and keywordto- caption augmentation, in: ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE. pp. 1-5."},{"key":"e_1_3_2_2_57_1","unstructured":"Yu J. Xu Y. Koh J.Y. Luong T. Baid G. Wang Z. Vasudevan V. Ku A. Yang Y. Ayan B.K. et al. 2022. Scaling autoregressive models for content-rich text-to-image generation. arXiv preprint arXiv:2206.10789 2 5."},{"key":"e_1_3_2_2_58_1","volume-title":"Musicmagus: Zero-shot text-to-music editing via diffusion models. arXiv preprint arXiv:2402.06178 .","author":"Zhang Y.","year":"2024","unstructured":"Zhang, Y., Ikemiya, Y., Xia, G., Murata, N., Mart\u00ednez-Ram\u00edrez, M.A., Liao, W.H., Mitsufuji, Y., Dixon, S., 2024. Musicmagus: Zero-shot text-to-music editing via diffusion models. arXiv preprint arXiv:2402.06178 ."}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Dublin Ireland","acronym":"MM '25"},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3754812","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:44:34Z","timestamp":1765309474000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3754812"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":58,"alternative-id":["10.1145\/3746027.3754812","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3754812","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}